PCHC: 多目的強化学習による嗜好条件付きヒューマノイド制御の実現
PCHC: Enabling Preference Conditioned Humanoid Control via Multi-Objective Reinforcement Learning
複数の競合する目的（速度とエネルギー消費など）をバランスするヒューマノイド制御のため、単一のポリシーで嗜好ベクトルに応じて多様な行動を生成できる多目的強化学習フレームワークを提案した。
詳しい要約
1. どんなもの？
2. 先行研究と比べてどこがすごい？
3. 技術・手法の肝は？
4. どうやって有効だと検証した？
5. 議論はある？
6. 次に読むべき論文は？
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Huanyu Li, Dewei Wang, Xinmiao Wang, Xinzhe Liu, Peng Liu, Chenjia Bai, Xuelong Li
分類: cs.RO
原文アブストラクト
Humanoid robots often need to balance competing objectives, such as maximizing speed while minimizing energy consumption. While current reinforcement learning (RL) methods can master complex skills like fall recovery and perceptive locomotion, they are constrained by fixed weighting strategies that produce a single suboptimal policy, rather than providing a diverse set of solutions for sophisticated multi-objective control. In this paper, we propose a novel framework leveraging Multi-Objective Reinforcement Learning (MORL) to achieve Preference-Conditioned Humanoid Control (PCHC). Unlike conventional methods that require training a series of policies to approximate the Pareto front, our framework enables a single, preference-conditioned policy to exhibit a wide spectrum of diverse behaviors. To effectively integrate these requirements, we introduce a Beta distribution-based alignment mechanism based on preference vectors modulating a Mixture-of-Experts (MoE) module. We validated our approach on two representative humanoid tasks. Extensive simulations and real-world experiments demonstrate that the proposed framework allows the robot to adaptively shift its objective priorities in real-time based on the input preference condition.
